internal static ITransformer Create(IHostEnvironment env, Options options, IDataView input)
{
Contracts.CheckValue(env, nameof(env));
var h = env.Register(LoaderSignature);
h.CheckValue(options, nameof(options));
h.CheckValue(input, nameof(input));
h.CheckUserArg(Utils.Size(options.Columns) > 0, nameof(options.Columns), "Columns must be specified");
var chain = new TransformerChain <ITransformer>();
// To each input column to the NgramHashExtractorArguments, a HashTransform using 31
// bits (to minimize collisions) is applied first, followed by an NgramHashTransform.
var hashColumns = new List <HashingEstimator.ColumnOptions>();
var ngramHashColumns = new NgramHashingEstimator.ColumnOptions[options.Columns.Length];
var colCount = options.Columns.Length;
// The NGramHashExtractor has a ManyToOne column type. To avoid stepping over the source
// column name when a 'name' destination column name was specified, we use temporary column names.
string[][] tmpColNames = new string[colCount][];
for (int iinfo = 0; iinfo < colCount; iinfo++)
{
var column = options.Columns[iinfo];
h.CheckUserArg(!string.IsNullOrWhiteSpace(column.Name), nameof(column.Name));
h.CheckUserArg(Utils.Size(column.Source) > 0 &&
column.Source.All(src => !string.IsNullOrWhiteSpace(src)), nameof(column.Source));
int srcCount = column.Source.Length;
tmpColNames[iinfo] = new string[srcCount];
for (int isrc = 0; isrc < srcCount; isrc++)
{
var tmpName = input.Schema.GetTempColumnName(column.Source[isrc]);
tmpColNames[iinfo][isrc] = tmpName;
hashColumns.Add(new HashingEstimator.ColumnOptions(tmpName, column.Source[isrc],
30, column.Seed ?? options.Seed, false, column.MaximumNumberOfInverts ?? options.MaximumNumberOfInverts));
}
ngramHashColumns[iinfo] =
new NgramHashingEstimator.ColumnOptions(column.Name, tmpColNames[iinfo],
column.NgramLength ?? options.NgramLength,
column.SkipLength ?? options.SkipLength,
column.UseAllLengths ?? options.UseAllLengths,
column.NumberOfBits ?? options.NumberOfBits,
column.Seed ?? options.Seed,
column.Ordered ?? options.Ordered,
column.MaximumNumberOfInverts ?? options.MaximumNumberOfInverts);
ngramHashColumns[iinfo].FriendlyNames = column.FriendlyNames;
}
var hashing = new HashingEstimator(h, hashColumns.ToArray()).Fit(input);
return(chain.Append(hashing)
.Append(new NgramHashingEstimator(h, ngramHashColumns).Fit(hashing.Transform(input)))
.Append(new ColumnSelectingTransformer(h, null, tmpColNames.SelectMany(cols => cols).ToArray())));
}
internal static IDataTransform Create(IHostEnvironment env, Options options, IDataView input,
TermLoaderArguments termLoaderArgs = null)
{
Contracts.CheckValue(env, nameof(env));
var h = env.Register(LoaderSignature);
h.CheckValue(options, nameof(options));
h.CheckValue(input, nameof(input));
h.CheckUserArg(Utils.Size(options.Columns) > 0, nameof(options.Columns), "Columns must be specified");
// To each input column to the NgramHashExtractorArguments, a HashTransform using 31
// bits (to minimize collisions) is applied first, followed by an NgramHashTransform.
IDataView view = input;
List <ValueToKeyMappingTransformer.Column> termCols = null;
if (termLoaderArgs != null)
{
termCols = new List <ValueToKeyMappingTransformer.Column>();
}
var hashColumns = new List <HashingEstimator.ColumnOptions>();
var ngramHashColumns = new NgramHashingEstimator.ColumnOptions[options.Columns.Length];
var colCount = options.Columns.Length;
// The NGramHashExtractor has a ManyToOne column type. To avoid stepping over the source
// column name when a 'name' destination column name was specified, we use temporary column names.
string[][] tmpColNames = new string[colCount][];
for (int iinfo = 0; iinfo < colCount; iinfo++)
{
var column = options.Columns[iinfo];
h.CheckUserArg(!string.IsNullOrWhiteSpace(column.Name), nameof(column.Name));
h.CheckUserArg(Utils.Size(column.Source) > 0 &&
column.Source.All(src => !string.IsNullOrWhiteSpace(src)), nameof(column.Source));
int srcCount = column.Source.Length;
tmpColNames[iinfo] = new string[srcCount];
for (int isrc = 0; isrc < srcCount; isrc++)
{
var tmpName = input.Schema.GetTempColumnName(column.Source[isrc]);
tmpColNames[iinfo][isrc] = tmpName;
if (termLoaderArgs != null)
{
termCols.Add(
new ValueToKeyMappingTransformer.Column
{
Name = tmpName,
Source = column.Source[isrc]
});
}
hashColumns.Add(new HashingEstimator.ColumnOptions(tmpName, termLoaderArgs == null ? column.Source[isrc] : tmpName,
30, column.Seed ?? options.Seed, false, column.MaximumNumberOfInverts ?? options.MaximumNumberOfInverts));
}
ngramHashColumns[iinfo] =
new NgramHashingEstimator.ColumnOptions(column.Name, tmpColNames[iinfo],
column.NgramLength ?? options.NgramLength,
column.SkipLength ?? options.SkipLength,
column.UseAllLengths ?? options.UseAllLengths,
column.NumberOfBits ?? options.NumberOfBits,
column.Seed ?? options.Seed,
column.Ordered ?? options.Ordered,
column.MaximumNumberOfInverts ?? options.MaximumNumberOfInverts);
ngramHashColumns[iinfo].FriendlyNames = column.FriendlyNames;
}
if (termLoaderArgs != null)
{
h.Assert(Utils.Size(termCols) == hashColumns.Count);
var termArgs =
new ValueToKeyMappingTransformer.Options()
{
MaxNumTerms = int.MaxValue,
Term = termLoaderArgs.Term,
Terms = termLoaderArgs.Terms,
DataFile = termLoaderArgs.DataFile,
Loader = termLoaderArgs.Loader,
TermsColumn = termLoaderArgs.TermsColumn,
Sort = termLoaderArgs.Sort,
Columns = termCols.ToArray()
};
view = ValueToKeyMappingTransformer.Create(h, termArgs, view);
if (termLoaderArgs.DropUnknowns)
{
var missingDropColumns = new (string outputColumnName, string inputColumnName)[termCols.Count];
